Presentation 2022-10-07
Towards Estimating Impressions on Images by Grouping Personalities Sharing Similar Sensibilities
Banri Kojima, Takahiro Komamizu, Kawanishi Yasutomo, Keisuke Doman, Ichiro Ide, Mitsuru Nakazawa, Yeongnam Chae, Bj?rn Stenger,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we study a method for estimating impressions that people receive from images. Impressions received from images differ from person to person, but there seems to be a certain stereotype regarding the tendency of these impressions. In this study, we focus on the attributes of people and investigate a method to improve the performance of impression estimation for images grouping attributes that are significantly related to the way impressions are received in a data-driven manner. However, it is not easy to collect a sufficient amount of data because attributes of people have large variety and their combinations are enormous. To solve this problem, a group of people with similar sensitivities are extracted by image clustering and person attribute clustering on the collected data, and then use an estimation model to realize impression estimation with a limited amount of data. Experimental results on a dataset of 4,000 carpet images annotated by 24 impression words indicate that attribute clustering is effective in improving the estimation accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Impression estimation / Clustering / Personal attributes
Paper # MVE2022-28
Date of Issue 2022-09-29 (MVE)

Conference Information
Committee MVE / VRSJ-SIG-MR / IPSJ-EC / HI-SIG-DeMO / VRSJ-SIG-CS
Conference Date 2022/10/6(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kiyoshi Kiyokawa(NAIST)
Vice Chair Sumaru Niida(KDDI Research)
Secretary Sumaru Niida(NAIST) / (DNP) / (Univ. of ToKyo) / (NTT)
Assistant Hidehiko Shishido(Univ. of Tsukuba) / Atsushi Nakazawa(Kyoto Univ.) / Naoya Tojo(KDDI Research) / Naoki Hagiyama(NTT)

Paper Information
Registration To Technical Committee on Media Experience and Virtual Environment / SIG-MR / Special Interest Group on Entertainment Computing / Special Interest Group on De-vice Media Oriented UI / SIG-CS
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Towards Estimating Impressions on Images by Grouping Personalities Sharing Similar Sensibilities
Sub Title (in English)
Keyword(1) Impression estimation
Keyword(2) Clustering
Keyword(3) Personal attributes
1st Author's Name Banri Kojima
1st Author's Affiliation Nagoya University(Nagoya Univ.)
2nd Author's Name Takahiro Komamizu
2nd Author's Affiliation Nagoya University(Nagoya Univ.)
3rd Author's Name Kawanishi Yasutomo
3rd Author's Affiliation Institute of Physical and Chemical Research(RIKEN)
4th Author's Name Keisuke Doman
4th Author's Affiliation Chukyo University(Chukyo Univ.)
5th Author's Name Ichiro Ide
5th Author's Affiliation Nagoya University(Nagoya Univ.)
6th Author's Name Mitsuru Nakazawa
6th Author's Affiliation Rakuten Group, Inc.(Rakuten)
7th Author's Name Yeongnam Chae
7th Author's Affiliation Rakuten Group, Inc.(Rakuten)
8th Author's Name Bj?rn Stenger
8th Author's Affiliation Rakuten Group, Inc.(Rakuten)
Date 2022-10-07
Paper # MVE2022-28
Volume (vol) vol.122
Number (no) MVE-200
Page pp.pp.57-62(MVE),
#Pages 6
Date of Issue 2022-09-29 (MVE)